Radial basis function-based image segmentation using a receptive field

This paper presents a novel method for CT head image automatic segmentation. The images are obtained from patients having the spontaneous intra cerebral brain hemorrhage (ICH). The results of the segmentation are images partitioned into ve regions of interest corresponding to four tissue classes (skull, brain, calci cations and ICH ) and background. Once the images are segmented it is possible to calculate various hemorrhage region parameters such as its size, position, etc. The segmentation is performed in three major steps. In the rst phase a feature extraction and normalization is performed using a receptive eld (RF). Experiments were performed to determine the optimal RF structure. Pixels are classi ed in the second phase using the radial basis function (RBF) arti cial neural network. Experiments with di erent RBF network topologies were performed in order to determine the optimal basis functions, network size and a training algorithm. The segmentation results obtained using the RBF network were compared with results obtained by multi-layer perceptron neural network (MLP). In the third phase the image regions obtained by the RBF network were labeled using an expert system. Experiments have shown that the proposed method successfully performs image segmentation.